codependix-export
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation for the codependix command-line utility. It does not include any scripts, automated triggers, or remote code fetch patterns. It focuses on explaining CLI flags and configuration options.\n- [INDIRECT_PROMPT_INJECTION]: The documentation mentions reading exported graphs in Mermaid or JSON format. While reading external data is a potential attack surface for indirect prompt injection, the skill describes the use of explicit HTML boundary markers (e.g., codependix:start and codependix:end) to delimit generated content, which is a recommended practice to reduce the risk of the agent misinterpreting data as instructions.
Audit Metadata